• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.173-181
• /
• 2017

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.141-149
• /
• 2007

Associating the shoulder line with head location of the human body is useful in verifying, localizing and tracking persons in an image. Since the head line and the shoulder line, what we call ${\Omega}$-shape, move together in a consistent way within a limited range of deformation, we can build a statistical shape model using Active Shape Model (ASM). However, when the conventional ASM is applied to ${\Omega}$-shape fitting, it is very sensitive to background edges and clutter because it relies only on the local edge or gradient. Even though appearance is a good alternative feature for matching the target object to image, it is difficult to learn the appearance of the ${\Omega}$-shape because of the significant difference between people's skin, hair and clothes, and because appearance does not remain the same throughout the entire video. Therefore, instead of teaming appearance or updating appearance as it changes, we model the discriminative appearance where each pixel is classified into head, torso and background classes, and update the classifier to obtain the appropriate discriminative appearance in the current frame. Accordingly, we make use of two features in fitting ${\Omega}$-shape, edge gradient which is used for localization, and discriminative appearance which contributes to stability of the tracker. The simulation results show that the proposed method is very robust to pose change, occlusion, and illumination change in tracking the head and shoulder line of people. Another advantage is that the proposed method operates in real time.

• Journal of The Korean Association For Science Education
• /
• v.33 no.6
• /
• pp.1154-1169
• /
• 2013

The present work was performed to find behavioral characteristics of elementary school students corresponding to the motivation system on science learning (SL-BIS/BAS; Behavioral Inhibition/Activation System about Science Learning) in the observation situation. Eye-tracking was used for this study, which is one of the neurophysiological methods. The findings of present study were as follows: First, students who have sensitive motivation system to SL-BIS (SL-BIS group) showed meaningfully shorter fixation duration the whole time during an observation task than students who have sensitive motivation system to SL-BAS (SL-BAS group) (p<.05). Total fixation counts of SL-BIS group were significantly larger than SL-BAS group and it indicates that SL-BIS group often generated new fixations. Therefore, fixation duration per count of SL-BAS group was longer than that of SLBIS group. Second, we studied fixations in situations with movement corresponding to the motivation system on science learning. SL-BIS group and SL-BAS group exhibited similar fixation duration in the study task segment with movement, which is one of the stimulus attracting students. However, for the study task segment when the movement was finished, total fixation duration and fixation duration per count of SL-BAS group were meaningfully longer than those of SL-BIS group. Third, comparing fixation targets classified by factors of study task, SL-BIS group showed fixation on the target that is not important for the study task. But SL-BAS group concentrated on the target-related factor of the study task. The present work could be helpful in understanding students' characteristics corresponding to the motivation system on science learning in observation situation and for making a learning & teaching plan that is suitable to the feature of students.